Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    expressions related to control over various aspects of life or decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.35
     يتيمه
    -0.35
     tâche
    -0.33
    expandindo
    -0.33
     InputDecoration
    -0.33
     peine
    -0.33
     Strukt
    -0.33
     Gefähr
    -0.32
    ulae
    -0.32
    encontra
    -0.32
    POSITIVE LOGITS
     controllable
    0.75
     control
    0.73
     autonomy
    0.66
     choice
    0.66
     controls
    0.65
     CONTROL
    0.63
    control
    0.62
     Control
    0.61
     contrôler
    0.61
     controlled
    0.60
    Act Density 0.397%

    No Known Activations